This was my first LoRA so is quite unstable, it's hard to find Checkpoints and parameters for good generations. If you have Tensor.art account you probably get better results in there, but even with that ....
Check the GALLERY generations to get some tips.
Description
Generation Example :
PROMPT:
1woman, ((mannequin)) with futuristic cyber clothes, dark red sexy tank top and black leather jacket in futuristic city, faceless, no face, no hair, no mouth, no ears, no nose, female_solo:1.3, ,SD 1.5,Science fiction
NEGATIVE PROMPT:
face, mouth, eyes, nose, ears, hair, bad-hands-5, body parts, lowres, bad anatomy, bad hands, extra legs, bad legs, extra arms, bad arm, extra body, bad body, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, background people
- MODEL:
Campur-Sari EVO V2
- LORAs:
Mannequin (This one)
Science fiction scenery - V1
- ControlNet:
OpenPose
Size:
Around 512px, and Upscale with HiresFix [Hires Steps: 25 Denoising Strength: 0.5]
Sampling Steps: 25
CFG Scale: 7
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.